返回
Engineering pupil function for optical adversarial attacks
DOI:10.1364/OE.450058.png)
摘要
En 中文
Adversarial attacks inject imperceptible noise to images to deteriorate the performance of deep image classification models. However, most of the existing studies consider attacks in the digital (pixel) domain where an image acquired by an image sensor with sampling and quantization is recorded. This paper, for the first time, introduces a scheme for optical adversarial attack, which physically alters the light field information arriving at the image sensor so that the classification model yields misclassification. We modulate the phase of the light in the Fourier domain using a spatial light modulator placed in the photographic system. The operative parameters of the modulator for adversarial attack are obtained by gradient-based optimization to maximize cross-entropy and minimize distortion. Experiments based on both simulation and a real optical system demonstrate the feasibility of the proposed optical attack. We show that our attack can conceal perturbations in the image more effectively than the existing pixel-domain attack. It is also verified that the proposed attack is completely different from common optical aberrations such as spherical aberration, defocus, and astigmatism in terms of both perturbation patterns and classification results. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
期刊
IF:
3.3
论文数:
6.1W
被引数:
14.3W
机构
引用论文
Deep learning based atmospheric turbulence compensation for orbital angular momentum beam distortion and communication
OPTICS EXPRESS
IF3.3
Machine-learning attacks on interference-based optical encryption: experimental demonstration
OPTICS EXPRESS
IF3.3
Plasma Hsp90 levels in patients with systemic sclerosis and relation to lung and skin involvement: a cross-sectional and longitudinal study系统性硬化症患者的血浆Hsp90水平及其与肺和皮肤受累的关系: 一项横断面和纵向研究
SCIENTIFIC REPORTS
IF3.9
From modeling to hardware: an experimental evaluation of image plane and Fourier plane coded compressive optical imaging
OPTICS EXPRESS
IF3.3

